{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,2]],"date-time":"2026-10-02T04:37:24Z","timestamp":1790915844062,"version":"4.1.0"},"reference-count":37,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2021,8,18]],"date-time":"2021-08-18T00:00:00Z","timestamp":1629244800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2021,8,18]],"date-time":"2021-08-18T00:00:00Z","timestamp":1629244800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Speech Technol"],"published-print":{"date-parts":[[2022,12]]},"DOI":"10.1007\/s10772-021-09883-3","type":"journal-article","created":{"date-parts":[[2021,8,18]],"date-time":"2021-08-18T16:02:47Z","timestamp":1629302567000},"page":"783-792","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":17,"title":["Speech emotion recognition using data augmentation"],"prefix":"10.1007","volume":"25","author":[{"given":"V. M.","family":"Praseetha","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"P. P.","family":"Joby","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2021,8,18]]},"reference":[{"issue":"2","key":"9883_CR1","first-page":"2015","volume":"1","author":"M Abadi","year":"2015","unstructured":"Abadi, M., Agarwal, A., Barham, P., Brevdo, E., Chen, Z., Citro, C., Corrado, G. S., Davis, A., Dean, J., Devin, M., & Ghemawat, S. (2015). Tensorflow: Large-scale machine learning on heterogeneous systems. Software Available from Tensorflow. Org, 1(2), 2015.","journal-title":"Software Available from Tensorflow. Org"},{"key":"9883_CR2","doi-asserted-by":"crossref","unstructured":"Bergstra, J., Breuleux, O., Bastien, F., Lamblin, P., Pascanu, R., Desjardins, G., Turian, J., Warde-Farley, D., & Bengio, Y. (2010). Theano: A CPU and GPU math compiler in python. In Proc. 9th Python in Science Conf, vol. 1, pp. 3\u201310.","DOI":"10.25080\/Majora-92bf1922-003"},{"key":"9883_CR3","doi-asserted-by":"crossref","unstructured":"Bhatti, M. W., Wang, Y., & Guan, L. (2004). A neural network approach for human emotion recognition in speech. In 2004 IEEE International Symposium on Circuits and Systems (IEEE Cat. No. 04CH37512) (Vol. 2, pp. II-181). IEEE.","DOI":"10.1109\/ISCAS.2004.1329238"},{"key":"9883_CR4","unstructured":"Chernykh, V., & Prikhodko, P. (2017). Emotion recognition from speech with recurrent neural networks. http:\/\/arxiv.org\/abs\/1701.08071."},{"issue":"1","key":"9883_CR5","doi-asserted-by":"publisher","first-page":"32","DOI":"10.1109\/79.911197","volume":"18","author":"R Cowie","year":"2001","unstructured":"Cowie, R., Douglas-Cowie, E., Tsapatsoulis, N., Votsis, G., Kollias, S., Fellenz, W., & Taylor, J. G. (2001). Emotion recognition in human\u2013computer interaction. IEEE Signal Processing Magazine, 18(1), 32\u201380.","journal-title":"IEEE Signal Processing Magazine"},{"issue":"4","key":"9883_CR6","doi-asserted-by":"publisher","first-page":"407","DOI":"10.1016\/j.neunet.2005.03.007","volume":"18","author":"L Devillers","year":"2005","unstructured":"Devillers, L., Vidrascu, L., & Lamel, L. (2005). Challenges in real-life emotion annotation and machine learning based detection. Neural Networks, 18(4), 407\u2013422.","journal-title":"Neural Networks"},{"key":"9883_CR7","doi-asserted-by":"crossref","unstructured":"Eyben, F., W\u00f6llmer, M., & Schuller, B. (2009). OpenEAR\u2014introducing the Munich open-source emotion and affect recognition toolkit. In ACII 2009. 3rd International Conference on Affective Computing and Intelligent Interaction and Workshops, (pp. 1\u20136). IEEE.","DOI":"10.1109\/ACII.2009.5349350"},{"key":"9883_CR8","unstructured":"Ghosh, S., Laksana, E., Morency, L. P., & Scherer, S. (2015). Learning representations of affect from speech. http:\/\/arxiv.org\/abs\/1511.04747."},{"key":"9883_CR9","doi-asserted-by":"crossref","unstructured":"Han, K., Yu, D., & Tashev, I. (2014). Speech emotion recognition using deep neural network and extreme learning machine. In Fifteenth annual conference of the International Speech Communication Association.","DOI":"10.21437\/Interspeech.2014-57"},{"issue":"03","key":"9883_CR10","doi-asserted-by":"publisher","first-page":"178","DOI":"10.36548\/jucct.2020.3.006","volume":"2","author":"W Haoxiang","year":"2020","unstructured":"Haoxiang, W. (2020). Emotional analysis of Bogus statistics in social media. Journal of Ubiquitous Computing and Communication Technologies (UCCT), 2(03), 178\u2013186.","journal-title":"Journal of Ubiquitous Computing and Communication Technologies (UCCT)"},{"key":"9883_CR11","doi-asserted-by":"crossref","unstructured":"Hu, H., Xu, M. X., & Wu, W. (2007). GMM supervector based SVM with spectral features for speech emotion recognition. In 2007 IEEE International Conference on Acoustics, Speech and Signal Processing-ICASSP'07 (Vol. 4, pp. IV-413). IEEE.","DOI":"10.1109\/ICASSP.2007.366937"},{"key":"9883_CR12","doi-asserted-by":"crossref","unstructured":"Huang, Z., Dong, M., Mao, Q., & Zhan, Y. (2014). Speech emotion recognition using CNN. In Proceedings of the 22nd ACM International Conference on Multimedia (pp. 801\u2013804).","DOI":"10.1145\/2647868.2654984"},{"issue":"02","key":"9883_CR13","first-page":"83","volume":"1","author":"IJ Jacob","year":"2019","unstructured":"Jacob, I. J. (2019). Capsule network based biometric recognition system. Journal of Artificial Intelligence, 1(02), 83\u201394.","journal-title":"Journal of Artificial Intelligence"},{"key":"9883_CR14","doi-asserted-by":"crossref","unstructured":"Kanda, N., Takeda, R., & Obuchi, Y. (2013). Elastic spectral distortion for low resource speech recognition with deep neural networks. In 2013 IEEE Workshop on Automatic Speech Recognition and Understanding (pp. 309\u2013314). IEEE.","DOI":"10.1109\/ASRU.2013.6707748"},{"key":"9883_CR15","doi-asserted-by":"crossref","unstructured":"Keren, G., & Schuller, B. (2016). Convolutional RNN: an enhanced model for extracting features from sequential data. In 2016 International Joint Conference on Neural Networks (IJCNN), (pp. 3412\u20133419). IEEE.","DOI":"10.1109\/IJCNN.2016.7727636"},{"key":"9883_CR16","doi-asserted-by":"crossref","unstructured":"Kim, Y., Lee, H., & Provost, E. M. (2013,). Deep learning for robust feature generation in audiovisual emotion recognition. In 2013 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), (pp. 3687\u20133691). IEEE.","DOI":"10.1109\/ICASSP.2013.6638346"},{"key":"9883_CR17","doi-asserted-by":"crossref","unstructured":"Ko, T., Peddinti, V., Povey, D., & Khudanpur, S. (2015). Audio augmentation for speech recognition. In Sixteenth Annual Conference of the International Speech Communication Association.","DOI":"10.21437\/Interspeech.2015-711"},{"key":"9883_CR18","doi-asserted-by":"crossref","unstructured":"Lee, J., & Tashev, I. (2015). High-level feature representation using recurrent neural network for speech emotion recognition. In Sixteenth Annual Conference of the International Speech Communication Association.","DOI":"10.21437\/Interspeech.2015-336"},{"issue":"01","key":"9883_CR19","doi-asserted-by":"publisher","first-page":"24","DOI":"10.36548\/jscp.2019.1.003","volume":"1","author":"S Manoharan","year":"2019","unstructured":"Manoharan, S. (2019). Study on Hermitian graph wavelets in feature detection. Journal of Soft Computing Paradigm (JSCP), 1(01), 24\u201332.","journal-title":"Journal of Soft Computing Paradigm (JSCP)"},{"key":"9883_CR20","doi-asserted-by":"crossref","unstructured":"Mao, X., Chen, L., & Fu, L. (2009). Multi-level speech emotion recognition based on HMM and ANN. In 2009 WRI World Congress on Computer Science and Information Engineering (Vol. 7, pp. 225\u2013229). IEEE.","DOI":"10.1109\/CSIE.2009.113"},{"issue":"8","key":"9883_CR21","doi-asserted-by":"publisher","first-page":"2203","DOI":"10.1109\/TMM.2014.2360798","volume":"16","author":"Q Mao","year":"2014","unstructured":"Mao, Q., Dong, M., Huang, Z., & Zhan, Y. (2014). Learning salient features for speech emotion recognition using convolutional neural networks. IEEE Transactions on Multimedia, 16(8), 2203\u20132213.","journal-title":"IEEE Transactions on Multimedia"},{"key":"9883_CR22","doi-asserted-by":"crossref","unstructured":"Neiberg, D., Elenius, K., & Laskowski, K. (2006). Emotion recognition in spontaneous speech using GMMs. In Ninth International Conference on Spoken Language Processing.","DOI":"10.21437\/Interspeech.2006-277"},{"issue":"4","key":"9883_CR23","doi-asserted-by":"publisher","first-page":"290","DOI":"10.1007\/s005210070006","volume":"9","author":"J Nicholson","year":"2000","unstructured":"Nicholson, J., Takahashi, K., & Nakatsu, R. (2000). Emotion recognition in speech using neural networks. Neural Computing & Applications, 9(4), 290\u2013296.","journal-title":"Neural Computing & Applications"},{"issue":"1","key":"9883_CR24","doi-asserted-by":"publisher","first-page":"116","DOI":"10.1109\/T-AFFC.2011.31","volume":"3","author":"S Ntalampiras","year":"2012","unstructured":"Ntalampiras, S., & Fakotakis, N. (2012). Modeling the temporal evolution of acoustic parameters for speech emotion recognition. IEEE Transactions on Affective Computing, 3(1), 116\u2013125.","journal-title":"IEEE Transactions on Affective Computing"},{"issue":"4","key":"9883_CR25","doi-asserted-by":"publisher","first-page":"603","DOI":"10.1016\/S0167-6393(03)00099-2","volume":"41","author":"TL Nwe","year":"2003","unstructured":"Nwe, T. L., Foo, S. W., & De Silva, L. C. (2003). Speech emotion recognition using hidden Markov models. Speech Communication, 41(4), 603\u2013623.","journal-title":"Speech Communication"},{"key":"9883_CR26","doi-asserted-by":"crossref","unstructured":"Prasomphan, S. (2015). Improvement of speech emotion recognition with neural network classifier by using speech spectrogram. In 2015 International Conference on Systems, Signals and Image Processing (IWSSIP) (pp. 73\u201376). IEEE.","DOI":"10.1109\/IWSSIP.2015.7314180"},{"key":"9883_CR27","doi-asserted-by":"crossref","unstructured":"Schuller, B., Rigoll, G., & Lang, M. (2003). Hidden Markov model-based speech emotion recognition. In 2003 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP'03). (Vol. 2, pp. II-1). IEEE.","DOI":"10.1109\/ICME.2003.1220939"},{"key":"9883_CR28","doi-asserted-by":"crossref","unstructured":"Schuller, B., Reiter, S., Muller, R., Al-Hames, M., Lang, M., & Rigoll, G. (2005). Speaker independent speech emotion recognition by ensemble classification. In IEEE International Conference on Multimedia and Expo. ICME 2005, (pp. 864\u2013867). IEEE.","DOI":"10.1109\/ICME.2005.1521560"},{"key":"9883_CR29","doi-asserted-by":"crossref","unstructured":"Stuhlsatz, A., Meyer, C., Eyben, F., Zielke, T., Meier, G., & Schuller, B. (2011). Deep neural networks for acoustic emotion recognition: Raising the benchmarks. In 2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (pp. 5688\u20135691). IEEE.","DOI":"10.1109\/ICASSP.2011.5947651"},{"key":"9883_CR30","doi-asserted-by":"crossref","unstructured":"Trigeorgis, G., Ringeval, F., Brueckner, R., Marchi, E., Nicolaou, M. A., Schuller, B., & Zafeiriou, S. (2016). Adieu features? End-to-end speech emotion recognition using a deep convolutional recurrent network. In 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (pp. 5200\u20135204). IEEE.","DOI":"10.1109\/ICASSP.2016.7472669"},{"key":"9883_CR31","doi-asserted-by":"crossref","unstructured":"Wang, S., Ling, X., Zhang, F., & Tong, J. (2010). Speech emotion recognition based on principal component analysis and back propagation neural network. In 2010 International Conference on Measuring Technology and Mechatronics Automation (Vol. 3, pp. 437\u2013440). IEEE.","DOI":"10.1109\/ICMTMA.2010.523"},{"key":"9883_CR32","doi-asserted-by":"crossref","unstructured":"Wang, Z. Q., & Tashev, I. (2017). Learning utterance-level representations for speech emotion and age\/gender recognition using deep neural networks. In 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), (pp. 5150\u20135154). IEEE.","DOI":"10.1109\/ICASSP.2017.7953138"},{"issue":"1","key":"9883_CR33","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TVCG.2017.2744878","volume":"24","author":"K Wongsuphasawat","year":"2017","unstructured":"Wongsuphasawat, K., Smilkov, D., Wexler, J., Wilson, J., Mane, D., Fritz, D., Krishnan, D., Vi\u00e9gas, F. B., & Wattenberg, M. (2017). Visualizing dataflow graphs of deep learning models in tensorflow. IEEE Transactions on Visualization and Computer Graphics, 24(1), 1\u201312.","journal-title":"IEEE Transactions on Visualization and Computer Graphics"},{"issue":"1","key":"9883_CR34","doi-asserted-by":"publisher","first-page":"10","DOI":"10.1109\/T-AFFC.2010.16","volume":"2","author":"CH Wu","year":"2011","unstructured":"Wu, C. H., & Liang, W. B. (2011). Emotion recognition of affective speech based on multiple classifiers using acoustic-prosodic information and semantic labels. IEEE Transactions on Affective Computing, 2(1), 10\u201321.","journal-title":"IEEE Transactions on Affective Computing"},{"key":"9883_CR35","doi-asserted-by":"crossref","unstructured":"Zheng, W. L., Zhu, J. Y., Peng, Y., & Lu, B. L. (2014). EEG-based emotion classification using deep belief networks. In 2014 IEEE International Conference on Multimedia and Expo (ICME), (pp. 1\u20136). IEEE.","DOI":"10.1109\/ICME.2014.6890166"},{"key":"9883_CR36","doi-asserted-by":"crossref","unstructured":"Zheng, W. Q., Yu, J. S., & Zou, Y. X. (2015). An experimental study of speech emotion recognition based on deep convolutional neural networks. In 2015 International Conference on Affective Computing and Intelligent Interaction (ACII) (pp. 827\u2013831). IEEE.","DOI":"10.1109\/ACII.2015.7344669"},{"key":"9883_CR37","doi-asserted-by":"crossref","unstructured":"Zhou, J., Wang, G., Yang, Y., & Chen, P. (2006). Speech emotion recognition based on rough set and SVM. In 2006 5th IEEE International Conference on Cognitive Informatics (Vol. 1, pp. 53\u201361). IEEE.","DOI":"10.1109\/COGINF.2006.365676"}],"container-title":["International Journal of Speech Technology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10772-021-09883-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10772-021-09883-3\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10772-021-09883-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,12]],"date-time":"2022-12-12T11:13:55Z","timestamp":1670843635000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10772-021-09883-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,8,18]]},"references-count":37,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2022,12]]}},"alternative-id":["9883"],"URL":"https:\/\/doi.org\/10.1007\/s10772-021-09883-3","relation":{},"ISSN":["1381-2416","1572-8110"],"issn-type":[{"value":"1381-2416","type":"print"},{"value":"1572-8110","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,8,18]]},"assertion":[{"value":"28 January 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 August 2021","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"18 August 2021","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}